Artificial neural network modeling for transistors and varactors in FinFET technology

Artificial neural networks (ANNs) have been applied as an efficient tool for modeling of different microwave devices. In this paper applications of ANNs for modeling devices fabricated in FinFET technology are examined. FinFET architecture is currently attracting a growing attention to enable further downscaling of the CMOS technology. As the interest towards the FinFET technology for microwave applications is not only limited to transistors but extended also to varactors, modeling of both transistors and varactors is considered. The models are developed for the actual devices after removing extrinsic effects by suitable de-embedding procedures. Verification of the models is done by comparing measured and simulated scattering parameters up to 50 GHz.